Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Claude Mythos Preview
99
Interfaze Beta
76
Verified leaderboard positions: Claude Mythos Preview #1 · Interfaze Beta unranked
Pick Claude Mythos Preview if you want the stronger benchmark profile. Interfaze Beta only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Knowledge
+15.0 difference
Multimodal
+21.3 difference
Claude Mythos Preview
Interfaze Beta
$25 / $125
$1.5 / $3.5
N/A
N/A
N/A
N/A
1M
1M
Pick Claude Mythos Preview if you want the stronger benchmark profile. Interfaze Beta only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Claude Mythos Preview is clearly ahead on the provisional aggregate, 99 to 76. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Mythos Preview's sharpest advantage is in multimodal & grounded, where it averages 92.4 against 71.1. The single biggest benchmark swing on the page is MMMU-Pro, 92.7% to 71.1%. Interfaze Beta does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Claude Mythos Preview is also the more expensive model on tokens at $25.00 input / $125.00 output per 1M tokens, versus $1.50 input / $3.50 output per 1M tokens for Interfaze Beta. That is roughly 35.7x on output cost alone.
Claude Mythos Preview is ahead on BenchLM's provisional leaderboard, 99 to 76. The biggest single separator in this matchup is MMMU-Pro, where the scores are 92.7% and 71.1%.
Interfaze Beta has the edge for knowledge tasks in this comparison, averaging 89.9 versus 74.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Mythos Preview has the edge for multimodal and grounded tasks in this comparison, averaging 92.4 versus 71.1. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.